Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cule
    -0.72
    ickle
    -0.69
    ãĥ¼ãĥĨãĤ£
    -0.68
    urt
    -0.67
     Eater
    -0.66
    ische
    -0.65
    ias
    -0.65
    ensor
    -0.65
    oret
    -0.64
    icit
    -0.63
    POSITIVE LOGITS
     departures
    0.73
    CHAT
    0.69
    APD
    0.69
    ategory
    0.67
     priesthood
    0.66
    MEN
    0.65
    ¥µ
    0.64
     abusers
    0.64
     tem
    0.63
    GROUND
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.